Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like features such as generalization, interpretability and human inter-operability. Inspired by the rich interactions between language and decision-making in humans, we introduce Policy Learning with a Language Bottleneck (PLLB), a framework enabling AI agents to generate linguistic rules that capture the strategies underlying their most rewarding behaviors. PLLB alternates between a rule generation step guided by language models, and an update step where agents learn new policies guided by rules. In a two-player communication game, a maze solving task, and two image reconstruction tasks, we show that PLLB agents are not only able to learn more interpretable and generalizable behaviors, but can also share the learned rules with human users, enabling more effective human-AI coordination.

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding catastrophic failures during training, which might severely impede both learning progress and the performance of the final policy. In many robotics settings, this amounts to avoiding certain "unsafe" states. The high-speed off-road driving task represents a particularly challenging instantiation of this problem: a high-return policy should drive as aggressively and as quickly as possible, which often requires getting close to the edge of the set of "safe" states, and therefore places a particular burden on the method to avoid frequent failures. To both learn highly performant policies and avoid excessive failures, we propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. Furthermore, we show that our risk-sensitive objective automatically avoids out-of-distribution states when equipped with an estimator for epistemic uncertainty. We implement our algorithm on a small-scale rally car and show that it is capable of learning high-speed policies for a real-world off-road driving task. We show that our method greatly reduces the number of safety violations during the training process, and actually leads to higher-performance policies in both driving and non-driving simulation environments with similar challenges.

Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute new insights into reinforcement learning algorithm design. The proposed adaptive exploration framework dynamically adjusts the exploration magnitude during training based on the recent performance of the agent. Our proposed method outperforms standard PPO algorithms in learning efficiency, particularly when significant exploratory behavior is needed at the beginning of the learning process.

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general $L$-layer neural network. New proof techniques are developed and an improved new $\tilde{\mathcal{O}}(\epsilon^{-1})$ sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an $\tilde{\mathcal{O}}(\epsilon^{-1})$ complexity under the Markovian sampling, as opposed to the best known $\tilde{\mathcal{O}}(\epsilon^{-2})$ complexity in the existing literature.

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause extrapolation error in the learning process. In many robotic applications, an inaccurate simulator is often available. However, the data directly collected from the inaccurate simulator cannot be directly used in offline RL due to the well-known exploration-exploitation dilemma and the dynamic gap between inaccurate simulation and the real environment. To address these issues, we propose a novel approach to combine the offline dataset and the inaccurate simulation data in a better manner. Specifically, we pre-train a generative adversarial network (GAN) model to fit the state distribution of the offline dataset. Given this, we collect data from the inaccurate simulator starting from the distribution provided by the generator and reweight the simulated data using the discriminator. Our experimental results in the D4RL benchmark and a real-world manipulation task confirm that our method can benefit more from both inaccurate simulator and limited offline datasets to achieve better performance than the state-of-the-art methods.

Stochastic optimization algorithms, particularly stochastic policy gradient (SPG), report significant success in reinforcement learning (RL). Nevertheless, up to now, that how to speedily acquire an optimal solution for RL is still a challenge. To tackle this issue, this work develops a fast SPG algorithm from the perspective of utilizing a momentum, coined SPG-NM. Specifically, in SPG-NM, a novel type of the negative momentum (NM) technique is applied into the classical SPG algorithm. Different from the existing NM techniques, we have adopted a few hyper-parameters in our SPG-NM algorithm. Moreover, the computational complexity is nearly same as the modern SPG-type algorithms, e.g., accelerated policy gradient (APG), which equips SPG with Nesterov's accelerated gradient (NAG). We evaluate the resulting algorithm on two classical tasks, bandit setting and Markov decision process (MDP). Numerical results in different tasks demonstrate faster convergence rate of the resulting algorithm by comparing state-of-the-art algorithms, which confirm the positive impact of NM in accelerating SPG for RL. Also, numerical experiments under different settings confirm the robustness of our SPG-NM algorithm for some certain crucial hyper-parameters, which ride the user feel free in practice.

One of the key challenges in current Reinforcement Learning (RL)-based Automated Driving (AD) agents is achieving flexible, precise, and human-like behavior cost-effectively. This paper introduces an innovative approach utilizing Large Language Models (LLMs) to intuitively and effectively optimize RL reward functions in a human-centric way. We developed a framework where instructions and dynamic environment descriptions are input into the LLM. The LLM then utilizes this information to assist in generating rewards, thereby steering the behavior of RL agents towards patterns that more closely resemble human driving. The experimental results demonstrate that this approach not only makes RL agents more anthropomorphic but also reaches better performance. Additionally, various strategies for reward-proxy and reward-shaping are investigated, revealing the significant impact of prompt design on shaping an AD vehicle's behavior. These findings offer a promising direction for the development of more advanced and human-like automated driving systems. Our experimental data and source code can be found here.

Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. However, it is also known that variations in the input (e.g., different colors of the panorama due to the season of the year) or the task (e.g., changing the speed limit for a car to respect) could require complete retraining of the agents. In this work, we leverage recent developments in unifying latent representations to demonstrate that it is possible to combine the components of an agent, rather than retrain it from scratch. We build upon the recent relative representations framework and adapt it for Visual RL. This allows us to create completely new agents capable of handling environment-task combinations never seen during training. Our work paves the road toward a more accessible and flexible use of reinforcement learning.

We study problems of federated control in Markov Decision Processes. To solve an MDP with large state space, multiple learning agents are introduced to collaboratively learn its optimal policy without communication of locally collected experience. In our settings, these agents have limited capabilities, which means they are restricted within different regions of the overall state space during the training process. In face of the difference among restricted regions, we firstly introduce concepts of leakage probabilities to understand how such heterogeneity affects the learning process, and then propose a novel communication protocol that we call Federated-Q protocol (FedQ), which periodically aggregates agents' knowledge of their restricted regions and accordingly modifies their learning problems for further training. In terms of theoretical analysis, we justify the correctness of FedQ as a communication protocol, then give a general result on sample complexity of derived algorithms FedQ-X with the RL oracle , and finally conduct a thorough study on the sample complexity of FedQ-SynQ. Specifically, FedQ-X has been shown to enjoy linear speedup in terms of sample complexity when workload is uniformly distributed among agents. Moreover, we carry out experiments in various environments to justify the efficiency of our methods.

This review article highlights state-of-the-art data-driven techniques to discover, encode, surrogate, or emulate constitutive laws that describe the path-independent and path-dependent response of solids. Our objective is to provide an organized taxonomy to a large spectrum of methodologies developed in the past decades and to discuss the benefits and drawbacks of the various techniques for interpreting and forecasting mechanics behavior across different scales. Distinguishing between machine-learning-based and model-free methods, we further categorize approaches based on their interpretability and on their learning process/type of required data, while discussing the key problems of generalization and trustworthiness. We attempt to provide a road map of how these can be reconciled in a data-availability-aware context. We also touch upon relevant aspects such as data sampling techniques, design of experiments, verification, and validation.